© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115794
    Prev
    Next
    INDEX
    Explanations

    U.S. and linux

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Garland
    -0.10
     intoxic
    -0.10
     porr
    -0.09
     DIR
    -0.09
     cra
    -0.09
     Dealer
    -0.09
     shar
    -0.09
     Conrad
    -0.09
     Dirt
    -0.09
     vis
    -0.09
    POSITIVE LOGITS
    stad
    0.10
    Wo
    0.10
     Owens
    0.09
     Wo
    0.09
    blr
    0.09
     prepar
    0.09
    kah
    0.09
     wo
    0.09
    -phase
    0.09
     Khal
    0.09
    Activations Density 0.002%

    No Known Activations